FailSAE: Towards Interpretable Failure Prediction for Vision-Language Models via Sparse Autoencoders
This story is from 2026-09-07. It is preserved in the archive; the latest stories are on the live feed.
arXiv:2609.04276v1 Announce Type: new Abstract: Vision-language models (VLMs), such as CLIP, have achieved strong performance across multimodal tasks by aligning visual and textual representations in a shared embedding space. As VLMs are increasingly used for high-stakes domains, failure prediction…
Read the full story at arXiv cs.CV ↗
Timeline · 1 report
- 2026-09-07 04:00 · arXiv cs.CV
FailSAE: Towards Interpretable Failure Prediction for Vision-Language Models via Sparse Autoencoders